{"id":"https://openalex.org/W2026191715","doi":"https://doi.org/10.1162/coli_a_00004","title":"Discourse Constraints for Document Compression","display_name":"Discourse Constraints for Document Compression","publication_year":2010,"publication_date":"2010-07-27","ids":{"openalex":"https://openalex.org/W2026191715","doi":"https://doi.org/10.1162/coli_a_00004","mag":"2026191715"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00004","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00004","pdf_url":"https://direct.mit.edu/coli/article-pdf/36/3/411/1812635/coli_a_00004.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/coli/article-pdf/36/3/411/1812635/coli_a_00004.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029852545","display_name":"James Clarke","orcid":"https://orcid.org/0009-0008-4111-2427"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James Clarke","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041024491","display_name":"Mirella Lapata","orcid":"https://orcid.org/0000-0002-2107-1516"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mirella Lapata","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029852545"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":5.5858,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.95598523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"36","issue":"3","first_page":"411","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8233233690261841},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7615863084793091},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6494402885437012},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5911600589752197},{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.5817582011222839},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5326696634292603},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5259552001953125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5232338309288025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.462527334690094},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.44915878772735596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07810670137405396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8233233690261841},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7615863084793091},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6494402885437012},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5911600589752197},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.5817582011222839},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5326696634292603},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5259552001953125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5232338309288025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.462527334690094},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.44915878772735596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07810670137405396},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_a_00004","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00004","pdf_url":"https://direct.mit.edu/coli/article-pdf/36/3/411/1812635/coli_a_00004.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.5850","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.5850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/J/J10/J10-3005.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:1138cbb54b4140378b3bb3007530cf29","is_oa":true,"landing_page_url":"https://doaj.org/article/1138cbb54b4140378b3bb3007530cf29","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 36, Iss 3 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00004","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00004","pdf_url":"https://direct.mit.edu/coli/article-pdf/36/3/411/1812635/coli_a_00004.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7511089076","display_name":null,"funder_award_id":"EP/F055765/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2026191715.pdf","grobid_xml":"https://content.openalex.org/works/W2026191715.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W40273907","https://openalex.org/W89646195","https://openalex.org/W98347854","https://openalex.org/W99221312","https://openalex.org/W418523852","https://openalex.org/W1498416817","https://openalex.org/W1535015163","https://openalex.org/W1535954793","https://openalex.org/W1552023264","https://openalex.org/W1565570978","https://openalex.org/W1566346388","https://openalex.org/W1573514622","https://openalex.org/W1597655096","https://openalex.org/W1664028424","https://openalex.org/W1710422233","https://openalex.org/W1714704734","https://openalex.org/W1964326564","https://openalex.org/W1972393702","https://openalex.org/W1994847495","https://openalex.org/W1999447745","https://openalex.org/W2001135856","https://openalex.org/W2002542884","https://openalex.org/W2005603124","https://openalex.org/W2007709031","https://openalex.org/W2008772536","https://openalex.org/W2015933299","https://openalex.org/W2040172363","https://openalex.org/W2042128417","https://openalex.org/W2045738181","https://openalex.org/W2050277298","https://openalex.org/W2065553296","https://openalex.org/W2066636486","https://openalex.org/W2076749875","https://openalex.org/W2078285016","https://openalex.org/W2082218603","https://openalex.org/W2086297729","https://openalex.org/W2094276686","https://openalex.org/W2101390659","https://openalex.org/W2104225263","https://openalex.org/W2110017317","https://openalex.org/W2111535382","https://openalex.org/W2115322217","https://openalex.org/W2116869842","https://openalex.org/W2117729721","https://openalex.org/W2117822433","https://openalex.org/W2118681326","https://openalex.org/W2120973168","https://openalex.org/W2123893795","https://openalex.org/W2124741472","https://openalex.org/W2128774237","https://openalex.org/W2130031580","https://openalex.org/W2133182690","https://openalex.org/W2138030222","https://openalex.org/W2140676672","https://openalex.org/W2140887277","https://openalex.org/W2142603219","https://openalex.org/W2144637381","https://openalex.org/W2145882814","https://openalex.org/W2145907631","https://openalex.org/W2163076329","https://openalex.org/W2165674742","https://openalex.org/W2170524863","https://openalex.org/W2251739113","https://openalex.org/W2432517183","https://openalex.org/W2442495973","https://openalex.org/W2973096875","https://openalex.org/W2981264952","https://openalex.org/W3150541299","https://openalex.org/W3151369355","https://openalex.org/W4231741839","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W3148229873","https://openalex.org/W4242223894","https://openalex.org/W2091301346","https://openalex.org/W2150160875","https://openalex.org/W1517524280","https://openalex.org/W4306886878","https://openalex.org/W4288365488","https://openalex.org/W2939976383"],"abstract_inverted_index":{"Sentence":[0],"compression":[1],"holds":[2],"promise":[3],"for":[4],"many":[5],"applications":[6,31],"ranging":[7],"from":[8],"summarization":[9],"to":[10],"subtitle":[11],"generation.":[12],"The":[13],"task":[14],"is":[15,46,59],"typically":[16],"performed":[17],"on":[18],"isolated":[19],"sentences":[20],"without":[21],"taking":[22],"the":[23,69],"surrounding":[24],"context":[25],"into":[26],"account,":[27],"even":[28],"though":[29],"most":[30],"would":[32],"operate":[33],"over":[34,80],"entire":[35],"documents.":[36],"In":[37],"this":[38],"article":[39],"we":[40],"present":[41],"a":[42,81],"discourse-informed":[43],"model":[44,58],"which":[45],"capable":[47],"of":[48,63,71],"producing":[49],"document":[50],"compressions":[51],"that":[52],"are":[53],"coherent":[54],"and":[55,66],"informative.":[56],"Our":[57],"inspired":[60],"by":[61],"theories":[62],"local":[64],"coherence":[65],"formulated":[67],"within":[68],"framework":[70],"integer":[72],"linear":[73],"programming.":[74],"Experimental":[75],"results":[76],"show":[77],"significant":[78],"improvements":[79],"state-of-the-art":[82],"discourse":[83],"agnostic":[84],"approach.":[85]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}